See Teng Jiek, Zhang Daokun, Boley Mario, Chalmers David K
Medicinal Chemistry, Monash Institute of Pharmaceutical Sciences, Monash University, 381 Royal Parade, Parkville, VIC 3068, Australia.
School of Computer Science, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo 315100, China.
J Chem Theory Comput. 2024 Oct 22;20(20):8886-8896. doi: 10.1021/acs.jctc.4c00798. Epub 2024 Oct 2.
Graph neural networks (GNNs) have emerged as powerful tools for quantum chemical property prediction, leveraging the inherent graph structure of molecular systems. GNNs depend on an edge-to-node aggregation mechanism for combining edge representations into node representations. Unfortunately, existing learnable edge-to-node aggregation methods substantially increase the number of parameters and, thus, the computational cost relative to simple sum aggregation. Worse, as we report here, they often fail to improve predictive accuracy. We therefore propose a novel learnable edge-to-node aggregation mechanism that aims to improve the accuracy and parameter efficiency of GNNs in predicting molecular properties. The new mechanism, called "patch aggregation", is inspired by the Multi-Head Attention and Mixture of Experts machine learning techniques. We have incorporated the patch aggregation method into the specialized, state-of-the-art GNN models SchNet, DimeNet++, SphereNet, TensorNet, and VisNet and show that patch aggregation consistently outperforms existing learnable and nonlearnable aggregation techniques (sum, multilayer perceptron, softmax, and set transformer aggregation) in the prediction of molecular properties such as QM9 thermodynamic properties and MD17 molecular dynamics trajectory energies and forces. We also find that patch aggregation not only improves prediction accuracy but also is parameter-efficient, making it an attractive option for practical applications for which computational resources are limited. Further, we show that Patch aggregation can be applied across different GNN models. Overall, Patch aggregation is a powerful edge-to-node aggregation mechanism that improves the accuracy of molecular property predictions by GNNs.
图神经网络（GNNs）已成为量子化学性质预测的强大工具，它利用了分子系统固有的图结构。GNNs依赖于一种边到节点的聚合机制，用于将边的表示组合成节点的表示。不幸的是，现有的可学习边到节点聚合方法大大增加了参数数量，从而相对于简单的求和聚合增加了计算成本。更糟糕的是，正如我们在此报告的那样，它们往往无法提高预测准确性。因此，我们提出了一种新颖的可学习边到节点聚合机制，旨在提高GNNs在预测分子性质时的准确性和参数效率。这种新机制称为“补丁聚合”，它受到多头注意力和专家混合机器学习技术的启发。我们已将补丁聚合方法纳入专门的、最先进的GNN模型SchNet、DimeNet++、SphereNet、TensorNet和VisNet，并表明在预测诸如QM9热力学性质以及MD17分子动力学轨迹能量和力等分子性质时，补丁聚合始终优于现有的可学习和不可学习聚合技术（求和、多层感知器、softmax和集合变换器聚合）。我们还发现，补丁聚合不仅提高了预测准确性，而且在参数方面效率很高，这使其成为计算资源有限的实际应用的一个有吸引力的选择。此外，我们表明补丁聚合可以应用于不同的GNN模型。总体而言，补丁聚合是一种强大的边到节点聚合机制，可提高GNNs对分子性质预测的准确性。
